© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 18116
    Prev
    Next
    INDEX
    Explanations

    events before holidays or specific dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ym
    -0.10
     Reaction
    -0.09
     reaction
    -0.09
    Reaction
    -0.08
     chauff
    -0.08
     Sext
    -0.08
     Clo
    -0.08
    ward
    -0.08
    Transient
    -0.08
    jah
    -0.08
    POSITIVE LOGITS
     Christmas
    0.16
     planned
    0.14
     indefinitely
    0.14
     christmas
    0.14
    Christmas
    0.13
     Planned
    0.12
     Thanksgiving
    0.12
    iro
    0.12
    iros
    0.12
     Easter
    0.12
    Activations Density 0.044%

    No Known Activations